Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 649 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.7505. Min Act: -0.0000

Data Index: 815114 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.8404. Min Act: -0.0000

Data Index: 402327 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.7531. Min Act: -0.0000

Data Index: 1000281 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5721. Min Act: -0.0000

Data Index: 355866 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5703. Min Act: -0.0000

Data Index: 274157 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5719. Min Act: -0.0000

Data Index: 1134368 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5230. Min Act: -0.0000

Data Index: 1189286 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5891. Min Act: -0.0000

Data Index: 625479 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.6812. Min Act: -0.0000

Data Index: 273817 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5746. Min Act: -0.0000

Data Index: 878482 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1353018 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4916. Min Act: -0.0000

Data Index: 157798 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1250845 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3949. Min Act: -0.0000

Data Index: 806775 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4817. Min Act: -0.0000

Data Index: 924312 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3922. Min Act: -0.0000

Data Index: 65307 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3726. Min Act: -0.0000

Data Index: 482767 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4487. Min Act: -0.0000

Data Index: 107663 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4316. Min Act: -0.0000

Data Index: 335913 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4086. Min Act: -0.0000

Data Index: 53696 (C4 (Web Text))

Max Activating Token Index: 364